Paused
🚀
VLM-RLAIF
Respository for ACL 2024 paper "Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI feedback"
-
-
Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback
Paper • 2402.03746 • Published -
SNUMPR/vlm_rlaif_video_llava_7b
Text Generation • Updated • 262 -
SNUMPR/vlm_sft_video_llava_7b
Updated • 8 -
SNUMPR/vlm_sft_video_llava_13b
Updated • 243 -
SNUMPR/vlm_rlaif_datasets
Preview • Updated • 12 • 1 -
SNUMPR/vlm_rlaif_train_anet_frames
Updated • 7 -
SNUMPR/vlm_rlaif_eval_datasets
Updated • 16 -
SNUMPR/vlm_rm_13b_lora
Updated -
SNUMPR/vlm_policy_init_7b_lora
Updated